Shannon McDowell (@sgmcdowell) header
Shannon McDowell (@sgmcdowell) profile picture

Founder of Transformative AI Solutions, AI Consultant, Music Producer (DMO Records), Social Introvert, Helping Others Learn About AI

Morristown, TN
Joined January 2011
Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)Photo by Shannon McDowell (@sgmcdowell)
My plugin website is officially live. As of now, the plugins are in Windows VST3 format only, but I do hope to get Audio Unit conversions accomplished ASAP. But all versions are useable in HTML. Please check out: Golpe Free lowfrequencygallery.com/inde…
51
Shannon McDowell retweeted
🚨 MAJOR BREAKING!!! WE DID IT!!! YOU MADE HISTORY!!! WTF AMERICA?! IS A NEW YORK TIMES BESTSELLER, DEBUTING AT #2!!! You DEFEATED attempts to suppress our book, cable networks that shut us out, and MAGA books by Newt Gingrich, Brian Kilmeade, and Peter Navarro pushed by the Fox machine. THEY HAD FOX. WE HAD YOU!!!
69
278
11
1,110
250,603
Shannon McDowell retweeted
4
9
703
Shannon McDowell retweeted
279
6,623
83
32,090
213,627
Shannon McDowell retweeted
1
9
23
325
Shannon McDowell retweeted
36
176
7
420
3,550
Shannon McDowell retweeted
16
27
1
77
895
Shannon McDowell retweeted
2
54
2
68
950
Shannon McDowell retweeted
2
47
1
92
1,053
Shannon McDowell retweeted
14
59
3
223
1,701
Shannon McDowell retweeted
13
85
6
130
1,286
Fortunately money isn't everything.
16
123
2
328
2,432
Shannon McDowell retweeted
your GrokBot hit 100% with 4 days left no reset coming. Elon Musk called it "unsustainably" expensive you're not using GrokBot too much. you're using it wrong in this article, I show 10 settings and copy-paste prompts that make your pool last all week:
176
70
15
598
541,001
Shannon McDowell retweeted
HOLY F*CK, ELON MUSK'S SPACEXAI TEAM JUST PUT 146 FREE GROK BOTS ONLINE, ONE CLICK EACH where to pick: → use cases: 56 jobs like inbox manager, invoice coordinator, subscription cleaner → marketplace: 90 bots like dial bot, figma bro, home robots how to add one: 1\ open the page that matches your problem 2\ pick the task you put off every week 3\ hit add 4\ set one rule: ask me first before it pays or calls anyone step 4 is the one people skip start with the chore you hate most both pages are linked below save this, then read the article below on building a Second Brain for your company with Grok Bot ↓
Andrej Karpathy’s LLM Wiki + Grok Bot A Second Brain that turns your knowledge into finished work Put your notes on a night shift before another week slips away The complete setup and prompts below ↓
17
33
2
269
32,083
Shannon McDowell retweeted
THIS IS AN ACTUAL F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: run Sonnet, Haiku 5.5 and Opus 5.5 at once, each one doing only the job it's best at. Better results and way fewer tokens, because every task lands on the right model. You just launch Claude Code like this: claude --model sonnet --advisor opus here's the split: → Sonnet 5.5 runs the session, writes the code and applies the fixes → Haiku 5.5 swarms the repo in parallel: search, grep and diff audits → Opus 5.5 stays on call as advisor for the big calls and signs off on the diff → you stop burning Opus context on work that doesn't need it Opus only steps in at three moments: → before a plan locks → when the same error shows up twice → before calling it done Sonnet builds. Haiku swarms. Opus reviews. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Sonnet 5.5 runs the main session and coordinates the work > search maps the repo on Haiku 5.5, read-only > grep finds call sites on Haiku 5.5 in its own context > audit checks the diff on Haiku 5.5 in a throwaway worktree > Opus 5.5 on call as advisor, reviews the synthesized diff before sign-off > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Reconfigure my Claude Code setup around this tree: 1. Run the main session on Sonnet 5.5 with Opus 5.5 as advisor. 2. Create three Haiku 5.5 subagents in .claude/agents: search (maps the repo), grep (finds call sites), audit (checks the diff). 3. Set isolation: worktree on audit so its checks never touch my working branch. 4. Add one rule to CLAUDE.md: delegate every repo search and test run to the Haiku 5.5 subagents to keep the main context small. 5. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ code.claude.com/docs/en/sub-… save it, it'll come in handy.
stop using grok bot like a chatbot the people getting crazy results don't have one smart bot. they have a f*cking org chart. how to build your first agent team from scratch: → chief of staff → specialists → skills + routines save this ↓
24
65
8
702
125,643
Shannon McDowell retweeted
43
143
1
517
3,259
Shannon McDowell retweeted
This
45
244
12
382
2,969
Shannon McDowell retweeted
ChatGPT has now a big problem. Researchers at Oxford exposed a massive threat to large language models.” It’s called "Model Collapse." And it explains why the internet is about to become a toxic waste dump for Large Language Models. Right now, AI companies are scraping the entire web to train their next-generation models. But there’s a massive problem. The internet is no longer just human data. It is rapidly filling up with AI-generated text, images, and code. What happens when an AI trains on data generated by another AI? A new paper in Nature just gave us the answer. And it is terrifying. When AI models are recursively trained on AI-generated data, they suffer from irreversible brain damage. The researchers found that the model starts forgetting the "tails" of the original data distribution. The rare, weird, unique, and complex human nuances completely disappear. It's like making a photocopy of a photocopy. Every generation loses resolution. The output gets flatter, blander, and more generic, until the model completely collapses in on itself. For years, we thought the biggest bottleneck for AI was compute, getting enough H100 GPUs from Nvidia. This paper proves the real bottleneck is us. If we keep flooding the internet with synthetic AI slop, we will poison the very data pool required to build smarter models. The ultimate irony? We thought AI was going to make human creators obsolete. Instead, this research proves that verified, genuine human data is about to become the most valuable commodity in the tech industry.
433
1,334
456
6,070
964,654
574
5,065
190
12,356
70,447
Shannon McDowell retweeted
Let America see the unredacted Epstein/Trump files immediately.
11
50
221
1,358